A Power Forecasting Method for Ultra-Short-Term Photovoltaic Power Generation Using Transformer Model

Abstract

The volatility of solar energy, geographic location, and weather factors continues to affect the stability of photovoltaic power generation, reliable and accurate photovoltaic power prediction methods not only effectively reduce the operating cost of the photovoltaic system but also provide reliable data support for the energy scheduling of the light storage microgrid, improve the stability of the photovoltaic system, and provide important help for the optimization operation of the photovoltaic system. Therefore, it is an important study to find reliable photovoltaic power prediction methods. In recent years, researchers have improved the accuracy of photovoltaic power generation forecasting by using deep learning models. Compared with the traditional neural network, the Transformer model can better learn the relationship between weather features and has good stability and applicability. Therefore, in this paper, the transformer model is used for predicting ultra-short-term photovoltaic power generation, and the photovoltaic power generation data and weather data in Hebei are selected. In the experiment, the prediction result of the transformer model was compared to the GRU and DNN models to show that the transformer model has better predictive ability and stability. Experimental results demonstrated that the proposed Transformer model outperforms the GRU model and DNN model by a difference of about 0.04 kW and 0.047 kW in the MSE value, and 22.0% and 29.1% of the MAPE error. In addition, the public DC competition dataset is selected for control experiments to demonstrate the general applicability of the transformer model for PV power prediction in different regions.

A Comprehensive Review of Artificial Intelligence Applications in the Photovoltaic Systems

“…Using the mean error as an indicator, the results show that the improved RBFN has a mean error of 0.0544 kW, which is 13% lower than the traditional RBFN method. Chang [105] used the real historical output power data to analyze the RBFN method, and the results show that the average absolute percentage error of RBFN method is 4.6785%, and the maximum absolute percentage deviation is 9.909 75%.…”

Optimize VMD-LSTM photovoltaic force combination prediction model based on SSA parameter optimization

“…Use error indicators, the average root error (RMSE), average absolute error (MAE), average absolute percentage error (MAPE), and fittings (R2) evaluate the results to end the algorithm. Among them, the smaller the RMSE, MAE, and MAPE indicators, the higher the predictive accuracy of the model; the closer to the R2, the higher the prediction accuracy, the more the calculation formula of each indicator is as follows Literature [14], [15] .…”

Towards energy efficiency: A comprehensive review of deep learning-based photovoltaic power forecasting strategies

“…The selection of these variables depends on their correlations with main PV power production, availability, and ease of access to such data. The most common variable used is measured power, employed in 67% of the recently published articles, such as [79] , [80] , [81] , [82] , [83] . This direct method captures the energy production behavior at specific times and locations.…”